From e6899174353f1e1a3604b3e8e63b92c9dffe10ac Mon Sep 17 00:00:00 2001
From: Yuneng Jiang <yuneng@berri.ai>
Date: Sat, 23 May 2026 10:48:56 -0700
Subject: [PATCH] test(bedrock): swap legacy claude-3/3.5 model strings for 4.5
 inference profiles

The pinned model IDs anthropic.claude-3-sonnet-20240229-v1:0 and
anthropic.claude-3-5-haiku-20241022-v1:0 are in the Bedrock 'public
extended access' phase of Legacy (EOL 2026-07-30 and 2026-06-19
respectively). Bedrock now returns ValidationException 'Operation not
allowed' for accounts that aren't grandfathered/active on these models,
which is what the CCI Bedrock-using account hits.

Swap to the current-generation inference profiles already used elsewhere
in the suite:

  - claude-3-5-haiku-20241022-v1:0       -> us.claude-haiku-4-5-20251001-v1:0
  - claude-3-sonnet-20240229-v1:0        -> us.claude-sonnet-4-5-20250929-v1:0
  - us.claude-3-sonnet-20240229-v1:0     -> us.claude-sonnet-4-5-20250929-v1:0
  - bedrock/claude-3-sonnet-20240229-v1:0 -> bedrock/us.claude-sonnet-4-5-20250929-v1:0

Affected tests:
  - tests/litellm_utils_tests/test_litellm_overhead.py
      test_litellm_overhead_non_streaming, test_litellm_overhead_stream
  - tests/local_testing/test_function_calling.py
      test_aaparallel_function_call, test_parallel_function_call_anthropic_error_msg,
      test_passing_tool_result_as_list
  - tests/test_openai_endpoints.py
      test_chat_completion_anthropic_structured_output
---
 tests/litellm_utils_tests/test_litellm_overhead.py | 5 ++---
 tests/local_testing/test_function_calling.py       | 9 ++++-----
 tests/test_openai_endpoints.py                     | 2 +-
 3 files changed, 7 insertions(+), 9 deletions(-)

diff --git a/tests/litellm_utils_tests/test_litellm_overhead.py b/tests/litellm_utils_tests/test_litellm_overhead.py
index 3a428e9d588..70fb42f33f5 100644
--- a/tests/litellm_utils_tests/test_litellm_overhead.py
+++ b/tests/litellm_utils_tests/test_litellm_overhead.py
@@ -14,7 +14,6 @@ sys.path.insert(
 )  # Adds the parent directory to the system path
 import litellm
 
-
 # Fake Vertex AI Gemini response for mocking
 FAKE_VERTEX_GEMINI_RESPONSE = {
     "candidates": [
@@ -82,7 +81,7 @@ async def _vertex_ai_mocks():
         "bedrock/mistral.mistral-7b-instruct-v0:2",
         "openai/gpt-4o",
         "openai/self_hosted",
-        "bedrock/anthropic.claude-3-5-haiku-20241022-v1:0",
+        "bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0",
         "vertex_ai/gemini-1.5-flash",
     ],
 )
@@ -147,7 +146,7 @@ async def test_litellm_overhead_non_streaming(model):
     [
         "bedrock/mistral.mistral-7b-instruct-v0:2",
         "openai/gpt-4o",
-        "bedrock/anthropic.claude-3-5-haiku-20241022-v1:0",
+        "bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0",
         "openai/self_hosted",
     ],
 )
diff --git a/tests/local_testing/test_function_calling.py b/tests/local_testing/test_function_calling.py
index 3c7e004b62e..1cad7d1421e 100644
--- a/tests/local_testing/test_function_calling.py
+++ b/tests/local_testing/test_function_calling.py
@@ -49,7 +49,7 @@ def get_current_weather(location, unit="fahrenheit"):
         "mistral/mistral-large-latest",
         "claude-haiku-4-5-20251001",
         "gemini/gemini-2.5-flash-lite",
-        "anthropic.claude-3-sonnet-20240229-v1:0",
+        "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
     ],
 )
 @pytest.mark.flaky(retries=3, delay=1)
@@ -267,7 +267,6 @@ def test_aaparallel_function_call_with_anthropic_thinking(model):
 
 from litellm.types.utils import ChatCompletionMessageToolCall, Function, Message
 
-
 _PARALLEL_TOOL_HISTORY_MESSAGES = [
     {
         "role": "user",
@@ -303,7 +302,7 @@ _PARALLEL_TOOL_HISTORY_MESSAGES = [
     [
         # Bedrock Converse still requires modify_params to inject the dummy tool.
         (
-            "anthropic.claude-3-sonnet-20240229-v1:0",
+            "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
             _PARALLEL_TOOL_HISTORY_MESSAGES,
             True,
         ),
@@ -314,7 +313,7 @@ _PARALLEL_TOOL_HISTORY_MESSAGES = [
             False,
         ),
         (
-            "anthropic.claude-3-sonnet-20240229-v1:0",
+            "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
             [
                 {
                     "role": "user",
@@ -579,7 +578,7 @@ def test_groq_parallel_function_call():
 @pytest.mark.parametrize(
     "model",
     [
-        "bedrock/anthropic.claude-3-sonnet-20240229-v1:0",
+        "bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0",
     ],
 )
 def test_passing_tool_result_as_list(model):
diff --git a/tests/test_openai_endpoints.py b/tests/test_openai_endpoints.py
index e898b88a556..29875a04413 100644
--- a/tests/test_openai_endpoints.py
+++ b/tests/test_openai_endpoints.py
@@ -446,7 +446,7 @@ async def test_chat_completion_anthropic_structured_output():
     client = AsyncOpenAI(api_key="sk-1234", base_url="http://0.0.0.0:4000")
 
     res = await client.beta.chat.completions.parse(
-        model="bedrock/us.anthropic.claude-3-sonnet-20240229-v1:0",
+        model="bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0",
         messages=messages,
         response_format=EventsList,
         timeout=60,